Non-contact type human iris recognition method for correcting a rotated iris image

Abstract

The present invention relates to an iris recognition method for correcting a rotated iris image. The iris image is acquired by an image acquisition device using an infrared illuminator. The inner and outer boundaries of the iris are detected by analyzing the differences in pixels using a Canny edge detector and the image for the inputted iris image, so as to allow the boundaries of the iris to be more accurately detected from the eye image of a user. If the iris image acquired has been rotated at an angle with respect to the centerline of the iris, the rotated iris image is corrected for subsequent authentication purposes.

Description

CLAIM OF PRIORITY[0001] This application makes reference to, incorporates the same herein, and claims all benefits accruing under 35 U.S.C. Section 119 from an application for "NON-CONTACT TYPE HUMAN IRIS RECOGNITION METHOD BY CORRECTION OF ROTATED IRIS IMAGE," filed earlier in the Korean Industrial Property Office on Mar. 6, 2001, and there duly assigned Ser. No. 2001-11441.[0002] 1. Field of Invention[0003] The present invention relates to a non-contact iris recognition method of authenticating the identity of a person. More particularly, the present invention relates to a method for correcting a rotated iris image during the authentication process.[0004] 2. Description of the Related Art[0005] An iris recognition system is used for identifying the identity of a person by distinguishing one's own particular iris pattern. The iris recognition system is superior in its accuracy in terms of personal identification compared to the other biometric methods, such as voice or fingerprint....

AI Technical Summary

Benefits of technology

[0010] Another aspect of the invention provides the method of detecting an iris image from the eye image of a user using an image acquisition device and converting the iris image in polar coordinates, wherein the inner and outer boundaries of an iris are detected using a Canny edge detector and infrared illuminator. The method of converting to the polar coordinates further includes the steps of: comparing the pixel value of the image information at the center coordinates (x, y) of the detected inner boundary of the iris with the other pixel values of image information, which is obtained by measuring the upward, downward, leftward, and rightward directions from the inner boundary; determining the maximum value among the compared pixel values and detecting the outer boundary of the iris; extracting an iris region, defining the region between the inner and outer boundaries; and, converting the extracted iris region into the polar coordinates.

[0009] One aspect of the present invention provides a human iris recognition method, such that in the event that the iris image is rotated by an angle, the rotated iris image is corrected into a normal iris image. To this end, the iris image with an irregular shape is converted into polar coordinates so that the slanted iris image is reflected at a lower portion of the converted iris image in the polar coordinates. Then the iris image is normalized to predetermined dimensions, so that the iris image with a variety of deformations is corrected.

[0010] Another aspect of the invention provides the method of detecting an iris image from the eye image of a user using an image acquisition device and converting the iris image in polar coordinates, wherein the inner and outer boundaries of an iris are detected using a Canny edge detector and infrared illuminator. The method of converting to the polar coordinates further includes the steps of: comparing the pixel value of the image information at the center coordinates (x, y) of the detected inner boundary of the iris with the other pixel values of image information, which is obtained by measuring the upward, downward, leftward, and rightward directions from the inner boundary; determining the maximum value among the compared pixel values and detecting the outer boundary of the iris; extracting an iris region, defining the region between the inner and outer boundaries; and, converting the extracted iris region into the polar coordinates.

Problems solved by technology

However, the conventional iris recognition system contains many errors in real applications.

Currently, most conventional iris recognition methods have drawbacks in that they cannot accurately detect the deformed or slanted eye image, other than manually readjusting the image after defining an arbitrary center of the pupil or using a mean value of the entire image to readjust the slanted image.

Images